New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Octocode Roast

by bgauryy in bgauryy/octocode

A skill your agent uses when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or…

MITAuto-check passedDevelopment

Install Octocode Roast

skills CLI
$ npx skills add bgauryy/octocode --skill octocode-roast -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bgauryy/octocode octocode-roast --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bgauryy/octocode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/octocode-roast .claude/skills/octocode-roast && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
octocode-roast
GitHub stars
949
Token cost
~999 tokens
SKILL.md length
461 words
Files
9 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or…

  • Code needs a blunt evidence-backed roast
  • SKILL.md covers Lobby rules, Severity, Smart routes — load only what… and Related routes, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Memorable critique: smell inventory

What it does

Octocode Roast is an agent skill from bgauryy/octocode. Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.

Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `README.md`, `references/improve-loop.md` and `references/language-sins.md`).

It sits in Development, covering Pull requests. It works with Model Context Protocol and GitHub. The repository describes itself as: Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI. The licence is MIT.

When your agent uses it

  • Code needs a blunt evidence-backed roast
  • Memorable critique: smell inventory
  • Hot-path autopsy
  • Savage/diff review

Example prompts

  • “/octocode-roast”

What it can do on your machine

Read from SKILL.md and the folder at commit c265e3f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Octocode Roast loads about 999 tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 461 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~999
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bgauryy/octocode at commit c265e3f, republished under its MIT licence (© bgauryy). 461 words, ~999 tokens.

Download SKILL.mdSave it as .claude/skills/octocode-roast/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
octocode-roast
description
Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.

Octocode Roast

Sharp code critique with proof and a repair path. Flow: TARGET → INSPECT → INVENTORY → AUTOPSY → CHECKPOINT → REDEEM.

Lobby rules

  • Target patterns, never people; obey the requested scope and widen only with approval.
  • Cite or drop it: every major finding needs an exact anchor, impact, confidence, and repair move.
  • Obey explicit user targets first. Only widen to staged/diff/repo scope when no target was given or the user asks for a broader pass.
  • Punch the code, not the coder; avoid insults about ability, identity, or experience.
  • Never reveal a secret; redact values and use restrained language for security or production-sensitive findings.
  • Rank confirmed security, data loss, correctness, and user-impacting performance above style or taste.
  • Default to medium tone; use savage/nuclear only when explicitly requested. Do not edit or install before consent.
  • Stop when: the target resolves to no files; the checkpoint is reached — important versus redundant findings summarized, nothing edited yet; a repair, a scope widening, or an install needs consent; savage/nuclear tone was not requested; or evidence is pattern-only — report the lead with its confidence instead of asserting exploitability, latency, or outage.

Severity

  • Capital offenses: confirmed secret exposure, injection/RCE paths, data loss or corruption, auth/access bypass.
  • Felonies: risky security controls, N+1 or hot-path performance damage, brittle async/concurrency, dangerous coupling, change-blocking god functions.
  • Crimes: broad type abuse, hidden state, poor errors, missing tests around risky logic.
  • Slop: duplicate ceremony, AI-ish verbosity, unclear naming, style residue that slows maintenance.
  • Misdemeanors: TODO fossils, console logs, formatting noise. If there are 20+ issues, triage the top 10 by impact and confidence, then separate important findings from redundant noise.
Show full SKILL.md (197 more words)Show less

Smart routes — load only what the current step needs

  • When you have the target and are ready to inspect it, load references/roast-playbook.md — the phase-by-phase run through inspection, inventory, autopsy, and the pre-fix checkpoint.
  • When building the inventory and ranking generic smells, load references/sin-catalog.md; for language-specific patterns or structural queries load references/language-sins.md — choose evidence appropriate to the code.
  • When the user picks repairs at the checkpoint, load references/redemption-flow.md — redeem findings through consent-gated fixes and verification.
  • When scope spans a monorepo or many categories, load references/parallel-roasting.md — split the inspection and inventory across workers without duplicating findings.
  • When research tooling is needed, load references/octocode.md and use octocode-research if available — verify before joking; mark reduced coverage otherwise.
  • When improving this skill, prefer octocode-graph-eval; otherwise load references/improve-loop.md — require an accept/revert criterion.
  • Use octocode-research for evidence gathering; octocode-graph-eval to measure roast usefulness; octocode-prompt-optimizer only for tone/instruction wording.
  • Use octocode-skills when changing this skill folder.

Output

Use: Top roast, Important findings, Redundant / low-value findings, Autopsy, Redemption paths, Fix checkpoint. Each finding includes file:line, evidence, impact, confidence, and repair move.

Scripts

None — this skill is instruction-only. Evidence comes from octocode-research and the host's own repo tools; verification runs the target project's own checks.

© bgauryy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in skills/octocode-roast of bgauryy/octocode.

  • SKILL.md
  • README.md
  • references/improve-loop.md
  • references/language-sins.md
  • references/octocode.md
  • references/parallel-roasting.md
  • references/redemption-flow.md
  • references/roast-playbook.md
  • references/sin-catalog.md

Open the folder on GitHubat commit c265e3f

Compare with similar skills

Octocode Roast next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Octocode Roast compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Octocode Roast this skillbgauryy/octocode949—~999Automated safety check: PassMIT
Plane Release Notes Generatormakeplane/plane61k—~2.5kAutomated safety check: PassAGPL-3.0
Mariadb Operator PR Reviewmariadb-operator/mariadb-operator1k—~3.3kAutomated safety check: PassApache-2.0
Link Ticket To SessionJayantDevkar/claude-code-karma329—~1.8kAutomated safety check: NotesApache-2.0
Code Reviewnteract/semiotic2.7k—~1.5kAutomated safety check: PassApache-2.0
PR Review Feedback Handlergittower/git-flow-next458—~2.9kAutomated safety check: NotesCustom licence

Similar skills

  • Plane Release Notes Generator

    makeplane/plane

    Builds categorized release notes for a Plane release pull request from its commits and writes them into the PR description, for both the plane-cloud and plane-ee repos.

    61k GitHub stars~2.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Mariadb Operator PR Review

    mariadb-operator/mariadb-operator

    Perform a structured maintainer-style PR review for the mariadb-operator repository.

    1k GitHub stars~3.3k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Link Ticket To Session

    JayantDevkar/claude-code-karma

    Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma.

    329 GitHub stars~1.8k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • Code Review

    nteract/semiotic

    Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence.

    2.7k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed

  • PR Review Feedback Handler

    gittower/git-flow-next

    Fetches review comments on a pull request, judges each one, writes the evaluation to a plan file and implements accepted changes, waiting for approval before anything public.

    458 GitHub stars~2.9k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

  • Trailsnap Commit

    LC044/TrailSnap

    TrailSnap 仓库提交、推送、需求平台与 PR 工作流规则。Use when preparing commits, pushing branches, managing the corresponding platform requirement, creating or merging pull requests, or monitoring PR CI in this…

    779 GitHub stars~557 tokensUpdated today
    DevelopmentAuto-check passed

More from bgauryy/octocode

All 12 skills in this repo

  • Octocode Benchmark Runner

    bgauryy/octocode

    Runs blind pairwise comparisons of Octocode against a gh-based baseline over markdown research questions, scored by total characters through the model rather than self-report.

    949 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed

  • Octocode Code Research

    bgauryy/octocode

    Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

    949 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

  • Evidence-Backed Documentation Writer

    bgauryy/octocode

    Writes, repairs and copyedits project docs against the Google developer documentation style guide, verifying claims in the repository before stating them.

    949 GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed

  • Octocode Mannequin

    bgauryy/octocode

    Poses and animates a 22-bone anatomical humanoid rig with joint range-of-motion limits, using a Node CLI, a Three.js viewer and WebMCP tools an agent can drive live.

    949 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Octocode Skills Manager

    bgauryy/octocode

    Finds, rates, reviews, creates, improves, installs and syncs Agent Skill folders from local workspaces, registries or remote sources, with a user gate before any write.

    949 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Octocode Brainstorming

    bgauryy/octocode

    Walks an idea through framing, diverging into options, researching evidence and stress-testing before converging on a build, prototype, narrow or park decision.

    949 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Octocode Roast

What does Octocode Roast do?

A skill your agent uses when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or…. Octocode Roast is an agent skill from bgauryy/octocode. Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths.

When should I use Octocode Roast?

Octocode Roast fits situations like: code needs a blunt evidence-backed roast; memorable critique: smell inventory; hot-path autopsy; savage/diff review.

How do I install Octocode Roast in Claude Code?

Run `npx skills add bgauryy/octocode --skill octocode-roast -a claude-code`. Or copy the skill folder (skills/octocode-roast in bgauryy/octocode) into .claude/skills/octocode-roast in your project. Claude Code loads it when a task matches its description.

How do I install Octocode Roast in Codex?

Run `npx skills add bgauryy/octocode --skill octocode-roast -a codex`. Or copy the skill folder (skills/octocode-roast in bgauryy/octocode) into .agents/skills/octocode-roast in your project. Codex loads it when a task matches its description.

Can I use Octocode Roast in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bgauryy/octocode --skill octocode-roast -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/octocode-roast, .gemini/skills/octocode-roast, .github/skills/octocode-roast and .opencode/skills/octocode-roast in your project.

What does Octocode Roast need to run?

SKILL.md names no scripts, command-line tools or credentials: Octocode Roast is instructions for the agent only.

Does Octocode Roast access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Octocode Roast safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Octocode Roast use?

Octocode Roast is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Octocode Roast use?

About 999 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Octocode Roast?

Skills that share tags, products or a category with Octocode Roast: Plane Release Notes Generator (makeplane/plane, 61k stars), Mariadb Operator PR Review (mariadb-operator/mariadb-operator, 1k stars), Link Ticket To Session (JayantDevkar/claude-code-karma, 329 stars) and Code Review (nteract/semiotic, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Octocode Roast?

bgauryy (a GitHub user) maintains it in bgauryy/octocode, which has 949 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.

Source: bgauryy/octocode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.